first commit

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "./",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "SEDIH",
+    "1": "MARAH",
+    "2": "CINTA",
+    "3": "TAKUT",
+    "4": "BAHAGIA"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "SEDIH": 0,
+    "MARAH": 1,
+    "CINTA": 2,
+    "TAKUT": 3,
+    "BAHAGIA": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "vocab_size": 32000
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 0.9759035977450284
+mcc = 0.5490295748196414

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "./output/cache", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 2, "encoding": null, "eval_batch_size": 1, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "cahya/distilbert-base-indonesian", "model_type": "distilbert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 200, "optimizer": "AdamW", "output_dir": "./output", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": false, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": "./output/logs", "thread_count": null, "tokenizer_name": "cahya/distilbert-base-indonesian", "tokenizer_type": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 2976, "weight_decay": 0.0, "model_class": "ClassificationModel", "labels_list": [0, 1, 2, 3, 4], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eceae1c1e51b1ab48b57f11cebca1c579aea6a386425767f7068196f181a42f3
+size 272409713

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "cahya/distilbert-base-indonesian", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3906030d92a0fcdbc1f0f2121f56b0822d4c3b7f86a6f2fe9c5bd9bf001075cd
+size 3183

training_progress_scores.csv

@@ -0,0 +1,6 @@
+global_step,train_loss,mcc,eval_loss
+248,1.4379340410232544,0.16794055118613757,1.513543146306818
+496,1.1409505605697632,0.4814009008917008,1.1180938720703124
+744,0.9938151240348816,0.5490295748196414,0.9759035977450284
+992,0.3853488564491272,0.5499300194670269,0.9965602527965199
+1240,0.5292290449142456,0.5277846910306091,1.0544361461292613